https://jira.whamcloud.com This file is an XML representation of an issue en-us 9.4.14 940014 05-12-2023 https://jira.whamcloud.com/browse/LU-4926 Lustre <p>This issue was created by maloo for nasf &lt;fan.yong@intel.com&gt;</p> <p>This issue relates to the following test suite run: <a href="http://maloo.whamcloud.com/test_sets/cb28be52-c631-11e3-874b-52540035b04c" class="external-link" target="_blank" rel="nofollow noopener">http://maloo.whamcloud.com/test_sets/cb28be52-c631-11e3-874b-52540035b04c</a>.</p> <p>The sub-test test_5 failed with the following error:</p> <blockquote> <p>Failed to copy files to mds2</p></blockquote> <p>Info required for matching: sanity-scrub 5</p> <p>Under a new formatted DNE environment, when copy file from local system to MDS2, it hit the failure of "Bad file descriptor".</p> LU-4926

sanity-scrub: Failed to copy files to mds2, Bad file descriptor

Bug Blocker Resolved Duplicate nasf Maloo Thu, 17 Apr 2014 23:45:23 +0000 Wed, 4 Jun 2014 23:15:40 +0000 Tue, 22 Apr 2014 07:10:45 +0000 0 5 <p>The attachment is the log for another failure instance. Seems related with CLIO.</p> <p>Jinshan, can you please give some check? Thanks.</p> <p>Nasf, are you able to reproduce this with manual testing? What steps do you take? It seems serious that a file cannot be copied to a new filesystem. Is there something that the test scripts are doing that might be hiding this bug from us?</p> <p>I can reproduce it by run sanity-scrub.sh with DNE enabled, but cannot reproduced it manually yet. I will investigate it more.</p> <p>The reason for the copy failure is that the mdc_intent_lock() does not fetch the LOV EA for the new created file, then its caller will call ll_prep_inode() to prepare the local object with empty stripe, and then the subsequent write operations with empty LOV EA will be regarded as invalid.</p> <div class="code panel" style="border-width: 1px;"><div class="codeContent panelContent"> <pre class="code-java">00000004:00000001:0.0:1395927909.641540:0:27857:0:(mdt_handler.c:750:mdt_getattr_internal()) <span class="code-object">Process</span> entered 00000004:00000040:0.0:1395927909.641540:0:27857:0:(mdt_handler.c:780:mdt_getattr_internal()) lustre-MDT0001: RPC from acaf5fbc-81d0-3a35-8cbb-3c2d460ad809: does not need LOVEA. ... 00000080:00000001:1.0:1395927909.641917:0:27983:0:(dcache.c:317:ll_revalidate_it_finish()) <span class="code-object">Process</span> entered 00000080:00000001:1.0:1395927909.641918:0:27983:0:(llite_lib.c:2411:ll_prep_inode()) <span class="code-object">Process</span> entered ... 00020000:00000002:1.0:1395927909.641948:0:27983:0:(lov_object.c:722:lov_layout_change()) [0x2c0002340:0x4f:0x0] from RAID0 to EMPTY ... 00000080:00000001:1.0:1395927909.642709:0:27983:0:(file.c:1355:ll_file_write()) <span class="code-object">Process</span> entered 00020000:00000001:1.0:1395927909.642730:0:27983:0:(lov_io.c:909:lov_io_init_empty()) <span class="code-object">Process</span> entered 00020000:00000001:1.0:1395927909.642730:0:27983:0:(lov_io.c:938:lov_io_init_empty()) <span class="code-object">Process</span> leaving (rc=1 : 1 : 1) 00000020:00000001:1.0:1395927909.642731:0:27983:0:(cl_io.c:179:cl_io_init0()) <span class="code-object">Process</span> leaving (rc=1 : 1 : 1) 00000020:00000001:1.0:1395927909.642731:0:27983:0:(cl_io.c:240:cl_io_rw_init()) <span class="code-object">Process</span> leaving (rc=1 : 1 : 1) 00000080:00000001:1.0:1395927909.642732:0:27983:0:(file.c:1189:ll_file_io_generic()) <span class="code-object">Process</span> leaving via out (rc=18446744073709551607 : -9 : 0xfffffffffffffff7) ... </pre> </div></div> <div class="code panel" style="border-width: 1px;"><div class="codeContent panelContent"> <pre class="code-java"><span class="code-object">int</span> lov_io_init_empty(<span class="code-keyword">const</span> struct lu_env *env, struct cl_object *obj, struct cl_io *io) { struct lov_object *lov = cl2lov(obj); struct lov_io *lio = lov_env_io(env); <span class="code-object">int</span> result; ENTRY; lio-&gt;lis_object = lov; <span class="code-keyword">switch</span> (io-&gt;ci_type) { <span class="code-keyword">default</span>: LBUG(); <span class="code-keyword">case</span> CIT_MISC: <span class="code-keyword">case</span> CIT_READ: result = 0; <span class="code-keyword">break</span>; <span class="code-keyword">case</span> CIT_FSYNC: <span class="code-keyword">case</span> CIT_SETATTR: result = +1; <span class="code-keyword">break</span>; <span class="code-keyword">case</span> CIT_WRITE: result = -EBADF; <span class="code-keyword">break</span>; <span class="code-keyword">case</span> CIT_FAULT: result = -EFAULT; CERROR(<span class="code-quote">"Page fault on a file without stripes: "</span>DFID<span class="code-quote">"\n"</span>, PFID(lu_object_fid(&amp;obj-&gt;co_lu))); <span class="code-keyword">break</span>; } <span class="code-keyword">if</span> (result == 0) { cl_io_slice_add(io, &amp;lio-&gt;lis_cl, obj, &amp;lov_empty_io_ops); cfs_atomic_inc(&amp;lov-&gt;lo_active_ios); } io-&gt;ci_result = result &lt; 0 ? result : 0; RETURN(result != 0); } </pre> </div></div> <p>In fact, such issue has been resolved by the patch <a href="http://review.whamcloud.com/#/c/9862/" class="external-link" target="_blank" rel="nofollow noopener">http://review.whamcloud.com/#/c/9862/</a>. I have repeatedly run sanity-scrub with such patch applied, and cannot reproduce the issue any longer.</p> <p>It is another failure instance of <a href="https://jira.whamcloud.com/browse/LU-4847" title="cl_default_mds_easize might be 0 in mdc_intent_getattr_pack" class="issue-link" data-issue-key="LU-4847"><del>LU-4847</del></a>.</p> Development Rank 1|hzwki7: Rank (Obsolete) 13616 Severity